Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quantities and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новременно
    0.89
     дослі
    0.81
     нами
    0.79
     चुंबकीय
    0.78
     числі
    0.78
     את
    0.77
    ലീസ്
    0.76
     Tentang
    0.75
     असल्यास
    0.75
     birlikte
    0.74
    POSITIVE LOGITS
    0.84
    ০০
    0.78
    moy
    0.74
    0
    0.71
     conformal
    0.66
    cester
    0.65
     compounds
    0.64
     ২০০
    0.64
     tinc
    0.62
     mark
    0.61
    Act Density 0.287%

    No Known Activations